Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base-10k-voxpopuli-ft-de](https://huggingface.co/facebook/wav2vec2-base-10k-voxpopuli-ft-de) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 8.7422
-- Wer: 1.0601
+- Loss: 1.8259
+- Wer: 0.1632
 
 ## Model description
 
@@ -51,11 +51,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.4701        | 10.87 | 500  | 5.1898          | 1.0499 |
-| 0.0817        | 21.74 | 1000 | 6.2573          | 1.0546 |
-| 0.0523        | 32.61 | 1500 | 6.8650          | 1.0567 |
-| 0.0248        | 43.48 | 2000 | 8.2037          | 1.0656 |
-| 0.0134        | 54.35 | 2500 | 8.7422          | 1.0601 |
+| 0.8086        | 5.43  | 250  | 0.8872          | 0.2456 |
+| 0.1358        | 10.87 | 500  | 1.1126          | 0.1858 |
+| 0.0916        | 16.3  | 750  | 1.5579          | 0.1991 |
+| 0.0716        | 21.74 | 1000 | 1.2674          | 0.1833 |
+| 0.0584        | 27.17 | 1250 | 1.6728          | 0.1768 |
+| 0.0464        | 32.61 | 1500 | 1.8259          | 0.1632 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca426e426c7302751861677099cb4a77d514f291133a3e2fe38a272f67b1700
+oid sha256:094f3b1ffb5f73d81031f28fd08e2de01c37e7946a189bec83d791c075729546
 size 377623376